Yazar "Haklidir, Mehmet" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Fuzzy control of calcium carbonate and silica scales in geothermal systems
    (Pergamon-Elsevier Science Ltd, 2017) Haklidir, Fusun Tut; Haklidir, Mehmet
    Calcium carbonate scaling and silica scaling are critical challenges directly affecting the efficiency of production during operational periods for geothermal power plants or geothermal district heating systems. Although their precipitation mechanisms are different from each other, both can be observed in varied proportions in production and reinjection wells as well as surface equipment in geothermal systems. Thus, scale prevention and control systems are essential, as abatement of scaling is more efficient than removal from wells and equipment after precipitation in a geothermal system. There are a few methods for control of silica and calcium carbonate precipitation in geothermal wells and surface equipment. Most production and reinjection wells require the implementation of a silica/calcium carbonate inhibition system to prevent silica/calcite precipitation inside casings, pipes, separators and other surface equipment in geothermal power systems. Installation of inhibitor systems are the most effective and practical solution for prevention of scaling problems and production loss, if the optimum inhibitor dosages are determined and applied effectively in geothermal systems. Less than optimum ratios of inhibitors may result in product overfeed, increased costs, and in some cases, inhibitor-induced fouling. The system is nonlinear and has multiple dependent and independent variables thus, it is difficult to obtain a mathematical model that describes the relation of geothermal fluid characteristic and inhibitors and with this reason, a fuzzy controller may be good option to resolve it in geothermal systems. Fuzzy control may replace the role of the mathematical model in conservative controllers, substituting it with a different model that is built from a number of smaller rules that only describe a sub-section of the complete system. In this study, two fuzzy logic controllers have been designed to control precipitation of silica and calcium carbonate by using scale inhibitors.
  • Küçük Resim Yok
    Öğe
    Prediction of geothermal originated boron contamination by deep learning approach: at Western Anatolia Geothermal Systems in Turkey
    (Springer, 2020) Haklidir, Fusun S. Tut; Haklidir, Mehmet
    Geothermal fluids consist of hot water, steam and gases in water-dominated reservoirs. They contain various dissolved major elements such as sodium, potassium, calcium, silica, bicarbonate, carbonate, chlorine, sulphate and minor elements such as boron, fluorine, lithium, iron, arsenic, mercury and bromine at different concentrations in the liquid phase. The concentration of dissolved solids depends on the temperature, gas content, reservoir geology, permeability, water mixing and fluid source of a geothermal system. Some of these species exhibit a toxic effect at high concentrations and require precaution after the discharging of geothermal water. Boron is one of the important constituents and can be observed as boric acid (H3BO3) or HBO2 in the water phase. The concentration of B changes between 10 and 50 ppm in chloride-type fluids and can occur in greater quantities than these values in organic-rich sedimentary rocks in geothermal fluids. Although boron is considered toxic, it is also one of the crude minerals and can be used in different industries, such as oil and gas chemistry, vehicle technologies, agriculture, ceramics, and adhesive and coating, among others. Machine learning is a method of data analytics for identifying patterns in data and using them to automatically make predictions about new data points. Deep learning is a machine learning subset that uses artificial neural networks with multiple layers. Deep learning can automatically learn representations from data without hand-coded rules or domain knowledge; this is the primary difference between deep learning and traditional machine learning techniques. In this study, a deep neural network model has been developed to predict boron concentrations based on hydrogeochemistry data for different geothermal systems. To compare the prediction performance of our proposed deep neural network model, two well-known regression approaches, linear regression and linear support vector machine (SVM), were performed, and the results have been presented. The performance comparison revealed that our deep neural network (DNN) model achieved better prediction performance than traditional machine learning techniques-linear regression and linear SVM.
  • Küçük Resim Yok
    Öğe
    Prediction of Reservoir Temperatures Using Hydrogeochemical Data, Western Anatolia Geothermal Systems (Turkey): A Machine Learning Approach
    (Springer, 2020) Haklidir, Fusun S. Tut; Haklidir, Mehmet
    Geothermal fluids can be used for purposes such as power production, district heating/cooling, agriculture, and industrial and thermal tourism. Although using geothermal fluids is beneficial, it requires detailed exploration studies of a region. These exploration studies mainly involve geology, geophysics and geochemistry disciplines to understand the location, dimensions, possible capacity and temperature of a reservoir before beginning drilling operations. Because of the high operational costs, the exploration phase of a geothermal project is of great importance to reduce project costs. Evaluation of existing earth sciences data, detailed geology studies, mapping and some geochemical studies, such as using geothermometers, can provide information about a potential geothermal reservoir in a geothermal field. Machine learning is a technology for data analysis which identifies patterns in data and uses them to make predictions about new data points automatically. In this study, a deep learning model is developed to predict geothermal reservoir temperatures based on selected hydrogeochemistry data from different geothermal systems. Two traditional regression approaches, linear regression and linear support vector machine, are performed to compare the prediction performance of our proposed deep learning model. The objective of the study is to obtain the algorithm having the lowest root-mean-square error and mean absolute error. The results show that the deep neural network (DNN) algorithm generated the lowest errors. The DNN model provided the most accurate values close to geothermometer calculations for reservoir temperature. The performance comparison showed that our deep learning model achieved the best prediction performance compared to traditional machine learning techniques.